Mistral AI
Mistral Small 22B
22B parameter model. Strong reasoning and multilingual. Needs 16GB+ RAM.
22B parametersmistralapache-2.032K context14.5GB - 14.5GB VRAM
Check Your Hardware
See which quantizations of Mistral Small 22B your hardware can run.
Quantization Options
| Quantization | Bits | File Size | VRAM Needed | RAM Needed | Quality |
|---|---|---|---|---|---|
| Q4_K_M | 4.5 | 13.3 GB | 14.5 GB | 18 GB | 85% |
See It In Action
Real model outputs generated via RunThisModel.com — watch responses stream in real time.
Llama 3.3 70B responding...
Outputs generated by real AI models via RunThisModel.com. Generation speed shown is from cloud inference. Local speeds vary by hardware — check your device.
Frequently Asked Questions
How much VRAM do I need to run Mistral Small 22B?
Mistral Small 22B requires 14.5GB VRAM minimum with Q4_K_M quantization. For full precision, you need 14.5GB VRAM.
What is the best quantization for Mistral Small 22B?
Q4_K_M offers the best balance of quality and VRAM usage. Q8_0 is near-lossless if you have enough VRAM.